Detect by line, instead of by blocks. [138765657]

Assigned

Feature Request

Status Update

No update yet.

Description

ro...@google.com

created issue #1

Aug 1, 2019 06:59AM

As with Amazon's Providing Key Value Pairs, customer would like to request to have the texts detected from PDF line by line, instead of by Blocks.

Comments

jo...@gmail.com <jo...@gmail.com> #2Dec 9, 2019 08:42PM

I have informed our engineering team of this feature request. There is currently no ETA for its implementation.

A current workaround would be to check the returned "boundingPoly" [1] "vertices" for the returned "textAnnotations". If the calculated rectangle's heights > widths, than your image is sideways.

[1]

https://cloud.google.com/vision/reference/rest/v1/images/annotate#boundingpoly

po...@gmail.com <po...@gmail.com> #3Feb 3, 2020 05:12PM

I also need this problem solved :)

so...@icsl.es <so...@icsl.es> #4Apr 14, 2020 06:02PM

same :D

Issue 138765657

Description

Issue summary

Comments

jo...@gmail.com <jo...@gmail.com> #2Dec 9, 2019 08:42PM

po...@gmail.com <po...@gmail.com> #3Feb 3, 2020 05:12PM

so...@icsl.es <so...@icsl.es> #4Apr 14, 2020 06:02PM

Add comment

Issue metadata